Switch wear degree prediction method and device, electronic equipment and vehicle

Abstract

The invention relates to a switch wear degree prediction method and device, electronic equipment and a vehicle, and relates to the technical field of vehicle detection.The method comprises the steps that pressing information of a target user for a vehicle switch at the current stage is obtained, and the pressing information comprises a springback speed sequence set and a springback depth sequence set; and calculating a wear degree evaluation value sequence based on the pressing information, and inputting the wear degree evaluation value sequence into the trained wear prediction model to obtain a wear degree prediction sequence of the vehicle switch in the next stage. According to the scheme disclosed by the invention, the wear degree of the vehicle switch in the next stage can be accurately predicted by utilizing the wear prediction model based on the pressing information of the vehicle switch in the current stage, and the prediction error of the wear degree of the switch can be reduced through the intelligent prediction mode, so that the safety of vehicle driving is ensured.

Description

Technical Field

[0001] The present disclosure relates to the field of vehicle detection technology, and in particular to a switch wear prediction method, device, electronic equipment and vehicle. Background Art

[0002] With the gradual progress of social science and technology, "Internet +" intelligent technology has gradually matured, and intelligent technology used in automobiles has also become more widespread, such as the use of car key switches. As the switch is used, it will cause wear and tear on the car switch. When the wear and tear of the switch is high, it is easy to cause traffic accidents.

[0003] At present, the wear degree of vehicle switches is mainly predicted by manual inspection, but this manual prediction method is prone to large prediction errors, which cannot guarantee the safety of vehicle driving. Summary of the invention

[0004] In view of this, the present disclosure provides a switch wear prediction method, device, electronic device and vehicle, the main purpose of which is to solve the technical problem that the current switch wear prediction has a large error and cannot ensure the safety of vehicle driving.

[0005] According to a first aspect of the present disclosure, a switch wear prediction method is provided, the method comprising:

[0006] Acquire the target user's pressing information on the vehicle switch at the current stage, wherein the pressing information includes a rebound speed sequence set and a rebound depth sequence set, wherein the rebound speed sequence set includes multiple rebound speed sequences under different pressure information, and the rebound depth sequence set includes multiple rebound depth sequences under different pressure information, and the pressure information includes at least pressure duration and pressure magnitude;

[0007] Calculating a first attenuation evaluation value sequence corresponding to the plurality of rebound speed sequences, and calculating a second attenuation evaluation value sequence corresponding to the plurality of rebound depth sequences;

[0008] Calculate the wear evaluation value sequence of the vehicle switch under different pressure information at the current stage by using the first attenuation evaluation value sequence and the second attenuation evaluation value sequence;

[0009] The wear evaluation value sequence is input into the trained wear prediction model to obtain the wear prediction sequence of the vehicle switch in the next stage.

[0010] According to a second aspect of the present disclosure, a switch wear prediction device is provided, the device comprising:

[0011] A first acquisition module is used to acquire the target user's pressing information on the vehicle switch at the current stage, wherein the pressing information includes a rebound speed sequence set and a rebound depth sequence set, wherein the rebound speed sequence set includes a plurality of rebound speed sequences under different pressure information, and the rebound depth sequence set includes a plurality of rebound depth sequences under different pressure information, and the pressure information includes at least pressure duration and pressure magnitude;

[0012] A first calculation module, used for calculating a first attenuation evaluation value sequence corresponding to the plurality of rebound speed sequences, and calculating a second attenuation evaluation value sequence corresponding to the plurality of rebound depth sequences;

[0013] A second calculation module, configured to calculate a wear evaluation value sequence of the vehicle switch under different pressure information at a current stage by using the first attenuation evaluation value sequence and the second attenuation evaluation value sequence;

[0014] The input module is used to input the wear evaluation value sequence into the trained wear prediction model to obtain the wear prediction sequence of the vehicle switch in the next stage.

[0015] According to the third aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method of the aforementioned first aspect.

[0016] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable a computer to execute the method of the aforementioned first aspect.

[0017] According to the fifth aspect of the present disclosure, a vehicle is provided, comprising at least one processor and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method as described in the first aspect above.

[0018] The switch wear prediction method, device, electronic device and vehicle provided by the present disclosure, compared with the prior art, obtain the target user's pressing information on the vehicle switch at the current stage, the pressing information includes a rebound speed sequence set and a rebound depth sequence set, the rebound speed sequence set includes multiple rebound speed sequences under different pressure information, the rebound depth sequence set includes multiple rebound depth sequences under different pressure information, and the pressure information at least includes pressure duration and pressure magnitude; calculate the first attenuation evaluation value sequence corresponding to the multiple rebound speed sequences, and calculate the second attenuation evaluation value sequence corresponding to the multiple rebound depth sequences; use the first attenuation evaluation value sequence and the second attenuation evaluation value sequence to calculate the wear evaluation value sequence of the vehicle switch under different pressure information at the current stage; input the wear evaluation value sequence into the trained wear prediction model to obtain the wear prediction sequence of the vehicle switch at the next stage. By applying the solution disclosed in the present invention, the wear prediction model can be used to accurately predict the wear degree of the vehicle switch in the next stage based on the pressing information of the vehicle switch in the current stage. Through this intelligent prediction method, the prediction error of the switch wear degree can be reduced, thereby facilitating accurate estimation of the remaining life of the switch during use and ensuring the safety of vehicle driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0020] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0021] Figure 1 A schematic diagram of a flow chart of a switch wear prediction method provided by an embodiment of the present disclosure;

[0022] Figure 2 A schematic flow chart of another switch wear prediction method provided by an embodiment of the present disclosure;

[0023] Figure 3 A schematic diagram of the structure of a switch wear prediction device provided by an embodiment of the present disclosure;

[0024] Figure 4 A schematic diagram of the structure of another switch wear prediction device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0025] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description. It should be noted that, in the absence of conflict, the embodiments of the present disclosure and the features in the embodiments may be combined with each other.

[0026] The switch wear prediction method, device, electronic device and vehicle according to the embodiments of the present disclosure are described below with reference to the accompanying drawings.

[0027] The present disclosure provides a switch wear prediction method, device, electronic equipment and vehicle, which can solve the current technical problem that the switch wear prediction error is large and thus the safety of vehicle driving cannot be guaranteed.

[0028] like Figure 1 As shown, an embodiment of the present disclosure provides a switch wear prediction method, comprising:

[0029] Step 101, obtaining the target user's pressing information on the vehicle switch at the current stage, the pressing information including a rebound speed sequence set and a rebound depth sequence set, the rebound speed sequence set including multiple rebound speed sequences under different pressure information, and the rebound depth sequence set including multiple rebound depth sequences under different pressure information.

[0030] The target user may be any person who presses the vehicle switch; the pressure information includes at least the pressure duration and pressure magnitude.

[0031] As a possible implementation method for the disclosed embodiment, the rebound speed may be detected using infrared light curtain technology to collect the light blocking speed of the vehicle switch under the light curtain, wherein the light blocking speed represents the rebound speed.

[0032] In specific application scenarios, since the vehicle switch may be affected by various factors during use, such as the key pressure of the vehicle switch, the duration of the key pressing, etc., the rebound speed of the vehicle switch shows a downward trend. Therefore, the rebound speed sequence under the same pressure and pressure time can be obtained, and the rebound speed sequence can be subsequently evaluated and analyzed for attenuation. Exemplarily, based on the same pressure and pressure time, 10,000 rated rebound speed data are measured, and every 100 rebound speed data are taken as a speed change sequence, which is recorded as a rebound speed sequence. A rebound speed sequence set {K1...K100} is obtained, which contains multiple rebound speed sequences.

[0033] For the disclosed embodiment, after the vehicle switch has been used for a period of time, under the influence of pressure and the time of pressure, the internal structure of the vehicle switch will be damaged, resulting in the vehicle switch being unable to return to its original state after being subjected to force, and then the rebound depth of the vehicle switch will change. The rebound depth of the vehicle switch will affect the degree of wear of the vehicle switch, so it is necessary to collect the rebound depth information. As a possible implementation method, the degree of deformation and rebound depth of the vehicle switch can be detected using infrared light curtain technology, and the degree of blocking of infrared light by the vehicle switch represents the rebound depth. Based on the same pressure and pressure time, while obtaining the rebound speed, the change of the rebound depth is obtained synchronously. The rated rebound depth data of 10,000 times is divided into 100 sequences every 100 times, that is, every 100 rebound depth data is regarded as a depth change sequence, that is, a rebound depth sequence, and a rebound depth sequence set {H1…,H100} is obtained, which contains multiple rebound depth sequences.

[0034] For the disclosed embodiment, the elastic quality of the vehicle switch will be worn out when it is used and pressed for a long time, resulting in a reduction in the life of the vehicle switch during use, which will affect the target user's process of pressing the vehicle switch. Under different pressures and pressure times, the rebound speed and rebound depth of the vehicle switch will have different changes, and different passengers have their own usage habits. When using the switch, the key pressure and pressure time are not the same, and under different pressures and pressure times, the impact on the vehicle switch is also different. Therefore, it is necessary to collect the pressure information of the vehicle switch.

[0035] As a possible implementation method, a pressure sensor can be used to collect the pressure information of the vehicle switch to detect the impact of different pressures and pressure times on the rebound speed and rebound depth. The target user's different pressures on the vehicle switch are collected to obtain a pressure sequence F = {F1, ...F i}, the greater the pressure, the greater the impact on the rebound speed and rebound depth of the vehicle switch. At the same time, when the pressure on the vehicle switch is longer under a certain pressure, the greater the impact on the rebound speed and rebound depth of the vehicle switch. Therefore, when collecting the vehicle pressure, the pressure duration under different pressures is also collected. Therefore, a pressure duration sequence M={M1,…M i}.

[0036] For the disclosed embodiment, the execution subject may be a switch wear prediction device. The switch wear prediction device obtains the target user's pressing information on the vehicle switch at the current stage, calculates the wear of the vehicle switch during use, and can predict the remaining service life of the vehicle switch during use in advance, so that maintenance can be performed before the vehicle switch fails, preventing failures from occurring during subsequent use and causing serious consequences.

[0037] Step 102: Calculate a first attenuation evaluation value sequence corresponding to a plurality of rebound velocity sequences, and calculate a second attenuation evaluation value sequence corresponding to a plurality of rebound depth sequences.

[0038] The first attenuation evaluation value is an attenuation index of the rebound speed of the vehicle switch during the pressing process; and the second attenuation evaluation value is an attenuation index of the rebound depth of the vehicle switch during the pressing process.

[0039] For the disclosed embodiment, when the target user presses the vehicle switch, the speed of the rebound of the vehicle switch can reflect the elasticity of the vehicle switch. When the rebound speed sequence is fast, it means that the elasticity of the vehicle switch is good, the wear of the vehicle switch is small, and the first attenuation evaluation value sequence is small; conversely, when the rebound speed is slow, it means that the elasticity of the vehicle switch is poor, the wear is large, and the first attenuation evaluation value sequence is large. When the target user presses the vehicle switch, the rebound depth of the vehicle switch will affect the wear of the vehicle switch. The corresponding second attenuation evaluation value sequence can be calculated through the difference between multiple rebound depth sequences. Therefore, the wear of the vehicle switch under different pressure sizes and pressure durations can be judged through the first attenuation evaluation value sequence and the second attenuation evaluation value sequence.

[0040] Step 103 : Calculate the wear evaluation value sequence of the vehicle switch under different pressure information at the current stage by using the first attenuation evaluation value sequence and the second attenuation evaluation value sequence.

[0041] Wear is the phenomenon of continuous loss of material on the surface of a material or residual deformation and fracture due to mechanical action, chemical reaction (including thermochemical, electrochemical and mechanochemical reactions). Wear is a surface phenomenon that occurs on an object, and its contact surface must have relative motion. Wear will inevitably cause material loss (including material transfer), and it is a gradual dynamic process with time-varying characteristics. The wear evaluation value is an indicator used to evaluate the degree of wear of automotive switches.

[0042] For the disclosed embodiment, since both the rebound speed and the rebound depth can reflect the wear of the vehicle switch, the wear of the vehicle switch is evaluated based on the obtained first attenuation evaluation value sequence and the second attenuation evaluation value sequence, and the wear evaluation value sequence of the vehicle switch under different pressure information at the current stage can be calculated.

[0043] Step 104 : Input the wear evaluation value sequence into the trained wear prediction model to obtain the wear prediction sequence of the vehicle switch in the next stage.

[0044] The wear prediction model is any model used to predict the wear degree of a vehicle switch, and may include but is not limited to a temporal convolutional network model (TCN). The temporal convolutional network model is an algorithm model used to solve time series prediction.

[0045] For the embodiments of the present disclosure, since the wear and tear generated during the use of the vehicle switch will reduce the service life of the vehicle switch, reduce the use efficiency of the vehicle switch and reduce the reliability of the vehicle switch, causing unsafe factors, by inputting the wear evaluation value sequence at the current stage into the trained wear prediction model, the wear prediction sequence at the next stage can be predicted, thereby facilitating accurate estimation of the remaining life of the switch during use, improving the use efficiency of the vehicle switch and the reliability of the vehicle switch, and reducing the accident rate during vehicle driving.

[0046] In summary, according to the switch wear prediction method, device, electronic device and vehicle provided by the present invention, compared with the prior art, the present invention obtains the target user's pressing information on the vehicle switch at the current stage, the pressing information includes a rebound speed sequence set and a rebound depth sequence set, the rebound speed sequence set includes multiple rebound speed sequences under different pressure information, the rebound depth sequence set includes multiple rebound depth sequences under different pressure information, and the pressure information at least includes pressure duration and pressure size; calculates a first attenuation evaluation value sequence corresponding to the multiple rebound speed sequences, and calculates a second attenuation evaluation value sequence corresponding to the multiple rebound depth sequences; uses the first attenuation evaluation value sequence and the second attenuation evaluation value sequence to calculate the wear evaluation value sequence of the vehicle switch under different pressure information at the current stage; inputs the wear evaluation value sequence into the trained wear prediction model to obtain a wear prediction sequence for the vehicle switch at the next stage. By applying the solution disclosed in the present invention, the wear prediction model can be used to accurately predict the wear degree of the vehicle switch in the next stage based on the pressing information of the vehicle switch in the current stage. Through this intelligent prediction method, the prediction error of the switch wear degree can be reduced, thereby facilitating accurate estimation of the remaining life of the switch during use and ensuring the safety of vehicle driving.

[0047] Further, as a refinement and extension of the above embodiment, in order to fully illustrate the specific implementation process of the method of this embodiment, this embodiment provides the following Figure 2 The specific method shown includes:

[0048] Step 201, obtaining the target user's pressing information on the vehicle switch at the current stage, the pressing information including a rebound speed sequence set and a rebound depth sequence set, the rebound speed sequence set including multiple rebound speed sequences under different pressure information, the rebound depth sequence set including multiple rebound depth sequences under different pressure information, and the pressure information at least including pressure duration and pressure magnitude.

[0049] For the implementation process of the embodiment of the present disclosure, please refer to the relevant description in step 101 of the embodiment, which will not be repeated here.

[0050] Step 202: Calculate multiple fitting velocity line slopes corresponding to multiple rebound velocity sequences using the least square method, and calculate multiple fitting depth line slopes corresponding to multiple rebound depth sequences using the least square method.

[0051] Among them, the least square method (also known as the least square method) is a mathematical optimization technique. It finds the best function matching of data by minimizing the sum of squares of errors. The least square method can be used to easily obtain unknown data and minimize the sum of squares of errors between the obtained data and the actual data. The least square method can also be used for curve fitting. Some other optimization problems can also be expressed by the least square method by minimizing energy or maximizing entropy.

[0052] For the disclosed embodiments, the least square method can be used to fit multiple rebound speed sequences to obtain multiple fitted rebound speed lines. Each rebound speed sequence corresponds to a fitted rebound speed line. Based on an arbitrary rebound speed sequence, the rebound speed sequence is linearly represented. Under ideal experimental conditions, the rebound speed of the vehicle switch decreases linearly. Therefore, a linear representation can be used to detect the data reliability of the rebound speed sequence. Multiple fitted rebound speed lines are obtained by fitting multiple rebound speed sequences respectively, and the fitted speed line slope calculation formula under the least square method is used to calculate the fitted speed line slope of the fitted rebound speed line.

[0053] The calculation formula for the slope of the fitted speed line includes:

[0054]

[0055] Where k1 represents the slope of the fitted velocity line, x represents the number of times the switch is pressed, and y1 represents the rebound velocity sequence.

[0056] Similarly, the least square method can be used to fit multiple rebound depth sequences to obtain multiple fitted rebound depth lines. Among them, each rebound depth sequence corresponds to a fitted rebound depth line. Based on any rebound depth sequence, the rebound depth sequence is linearly represented. In an ideal experimental situation, the rebound depth of the automotive switch decreases linearly. Therefore, a linear representation can be used to detect the data reliability of the rebound depth sequence. Multiple fitted rebound depth lines are obtained by fitting multiple rebound depth sequences respectively, and the fitted depth line slope of the fitted rebound depth line is calculated using the fitting depth line slope calculation formula under the least square method.

[0057] The calculation formula for the slope of the fitted depth line includes:

[0058]

[0059] Where k2 represents the slope of the fitted depth line, x represents the number of times the switch is pressed, and y2 represents the rebound depth sequence.

[0060] Step 203: Based on the slopes of multiple fitted speed lines, the rebound velocity attenuation evaluation values ​​under different pressure information are calculated respectively to obtain a first attenuation evaluation value sequence including multiple rebound velocity attenuation evaluation values; based on the slopes of multiple fitted depth lines, the rebound depth attenuation evaluation values ​​under different pressure information are calculated respectively to obtain a second attenuation evaluation value sequence including multiple rebound depth attenuation evaluation values.

[0061] According to the difference between the slopes of each fitting speed line under the action of different pressure information, a plurality of rebound speed attenuation evaluation values ​​are obtained. The specific implementation process can be described as follows: the minimum fitting speed line slope and the maximum fitting speed line slope are screened from the plurality of fitting speed line slopes; for each of the plurality of fitting speed line slopes, based on the minimum fitting speed line slope and the maximum fitting speed line slope, the calculation process of the rebound speed attenuation evaluation value is repeatedly executed until a first attenuation evaluation value sequence corresponding to the plurality of rebound speed sequences is obtained; wherein the calculation process of the rebound speed attenuation evaluation value includes: determining any fitting speed line slope from the plurality of fitting speed line slopes as the target fitting speed line slope; calculating a first slope difference between the target fitting speed line slope and the minimum fitting speed line slope, and a second slope difference between the maximum fitting speed line slope and the target fitting speed line slope, and determining the ratio of the first slope difference to the second slope difference as the rebound speed attenuation evaluation value under the action of the pressure information corresponding to the target fitting speed line slope.

[0062] According to the difference between the slopes of each fitting depth line under the action of different pressure information, multiple rebound depth attenuation evaluation values ​​are obtained. The specific implementation process can be described as: screening the minimum fitting depth line slope and the maximum fitting depth line slope from the multiple fitting depth line slopes; for each fitting depth line slope among the multiple fitting depth line slopes, based on the minimum fitting depth line slope and the maximum fitting depth line slope, repeatedly executing the calculation process of the rebound depth attenuation evaluation value until a second attenuation evaluation value sequence corresponding to the multiple rebound depth sequences is obtained; wherein, the calculation process of the rebound depth attenuation evaluation value includes: determining any fitting depth line slope among the multiple fitting depth line slopes as the target fitting depth line slope; calculating the third slope difference between the target fitting depth line slope and the minimum fitting depth line slope, and the fourth slope difference between the maximum fitting depth line slope and the target fitting depth line slope, and determining the ratio of the third slope difference to the fourth slope difference as the rebound depth attenuation evaluation value under the action of the pressure information corresponding to the target fitting depth line slope.

[0063] Step 204 : Calculate the wear evaluation value sequence of the vehicle switch under different pressure information at the current stage by using the first attenuation evaluation value sequence and the second attenuation evaluation value sequence.

[0064] For the disclosed embodiment, since both the rebound speed and the rebound depth can reflect the wear of the vehicle switch, the wear of the vehicle switch is evaluated based on the multiple rebound speed attenuation evaluation values ​​and the multiple rebound depth attenuation evaluation values ​​obtained to obtain multiple wear evaluation values.

[0065] The calculation formula of wear evaluation value is:

[0066]

[0067] Where U i represents the wear evaluation value sequence corresponding to the i-th first attenuation evaluation value sequence and the i-th second attenuation evaluation value sequence, W i is the first attenuation evaluation value sequence corresponding to the i-th rebound depth sequence, H i is the second attenuation evaluation value sequence corresponding to the i-th rebound velocity sequence.

[0068] The first attenuation evaluation value sequence and the second attenuation evaluation value sequence are used to calculate the wear evaluation value sequence of the vehicle switch under different pressure information at the current stage. The specific implementation process can be described as: based on the first attenuation evaluation value sequence and the second attenuation evaluation value sequence, the rebound velocity attenuation evaluation value and the rebound depth attenuation evaluation value under different pressure information are multiplied to obtain the target attenuation evaluation value sequence under different pressure information; the inverse of the sum of the target attenuation evaluation value sequence and 1 is determined as the wear evaluation value sequence of the vehicle switch under different pressure information.

[0069] Step 205: Input the wear evaluation value sequence into the trained wear prediction model to obtain the wear prediction sequence of the vehicle switch in the next stage.

[0070] For the disclosed embodiment, the wear prediction model is trained in advance. First, the sample pressing information of the target user is obtained. The sample pressing information includes the first wear evaluation value sequence of the vehicle switch in the first historical stage under different pressure information, and the second wear evaluation value sequence of the second wear evaluation value sequence in the second historical stage. The second historical stage is the next stage of the first historical stage. Due to the different wear degrees caused to the vehicle switch under different pressure information, the lower the pressure information, the smaller the wear caused when the vehicle switch is subjected to force, and vice versa. When the pressure information is close, the wear degree caused to the vehicle switch is also close, so the difference in pressure information reflects the difference in wear degree. Therefore, in order to facilitate subsequent grouping, it is necessary to calculate the similarity of the wear degree change sequence of the first wear evaluation value sequence under different pressure information. The larger the absolute value of the difference corresponding to different pressure information, the more similar the similarity of the different first wear evaluation value sequences is; conversely, the smaller the absolute value of the difference corresponding to different pressure information, the less similar the similarity of the different first wear evaluation value sequences is. The value range of the similarity is [0, 1]. The more similar the change trends and values ​​of different first wear degree evaluation value sequences are, the closer the value of the similarity is to 1, and vice versa.

[0071] As a possible implementation method, the similarity of different first wear degree evaluation value sequences may be calculated by calculating the mass loss influence of the first wear degree evaluation value sequences under the action of different pressure information.

[0072] The mass loss influence degree of the first wear degree evaluation value sequence under different pressure information is calculated. The specific implementation process can be described as follows: extracting the maximum pressure duration, the minimum pressure duration, the maximum pressure magnitude and the minimum pressure magnitude from different pressure information; substituting each pressure information, the maximum pressure duration, the minimum pressure duration, the maximum pressure magnitude and the minimum pressure magnitude into the mass loss influence degree calculation formula to obtain the mass loss influence degree of the first wear degree evaluation value sequence under different pressure information;

[0073] Among them, the calculation formula for the degree of quality loss includes:

[0074]

[0075] In the formula, Q1 represents the degree of quality loss, F i Indicates the magnitude of each pressure in different pressure information, F Min Indicates the minimum pressure, FMax Indicates the maximum pressure, M i Indicates the current pressure time, M Min Indicates the minimum pressure duration, M Max Indicates the duration of maximum pressure.

[0076] As a possible implementation method, the first mass loss influence degree under the first pressure information and the first wear evaluation value sequence corresponding to the first pressure information, as well as the second mass loss influence degree under the second pressure information and the second wear evaluation value sequence corresponding to the second pressure information can be respectively substituted into the similarity value calculation formula to obtain the similarity values ​​of the wear evaluation value sequences under different pressure times;

[0077] The similarity value calculation formula includes:

[0078]

[0079] Where U A represents the first wear evaluation value sequence, U B represents any wear evaluation value sequence in the first historical stage, Q A Indicates the influence degree of the first mass loss under the first pressure information, Q B Indicates the influence degree of the second mass loss under the second pressure information.

[0080] As a possible implementation method, the similarity value can be used to calculate the sample distance required for clustering, and the DBSCAN density clustering algorithm can be used to group the first wear evaluation value sequence according to the sample distance. The method for obtaining the sample distance can be: the inverse of the product of the first similarity value corresponding to the first wear evaluation value sequence and the second similarity value corresponding to any wear evaluation value sequence in the first historical stage plus 1 is used as the sample distance between the first wear evaluation value sequence and the arbitrary wear evaluation value sequence. The larger the sample distance value between the first wear evaluation value sequence and the arbitrary wear evaluation value sequence, the more similar the two wear evaluation value sequences are, and the corresponding pressure information is also similar. The first wear evaluation value sequence is grouped using the DBSCAN density clustering algorithm, and a search radius r is set, and the search range is determined by the r value, and the grouping range is determined. So far, multiple groups can be obtained, and the implementer can adjust the r value appropriately according to the actual situation.

[0081] By fusing multiple first wear evaluation value sequences in the same group into a total wear evaluation value sequence; obtaining the sum of the sample distances between any two first wear evaluation values ​​in the total wear evaluation value sequence, and adding 1 to the inverse of the sum of the sample distances as the confidence. Each group corresponds to a confidence. The higher the confidence, the higher the credibility of the corresponding group; conversely, the lower the confidence, the lower the credibility of the corresponding group. The confidence is normalized to a sample weight C = {C1, .., C i}.

[0082] When training the wear prediction model, the first wear evaluation value sequence is used as the input feature of the wear prediction model, and the second wear evaluation value sequence is used as the training label of the wear prediction model. The wear prediction model is iteratively trained based on the confidence until the loss function value of the wear prediction model is less than the preset threshold, and the wear prediction model training is judged to be completed. Among them, the loss function is calculated based on the sample weight of the confidence, and the loss function calculation formula is:

[0083]

[0084] In the formula, Loss represents the loss function value, represents the second wear evaluation value sequence, y i represents the first wear evaluation value sequence, C i represents the sample weight.

[0085] After the wear prediction model training is completed, the wear evaluation value sequence corresponding to any pressure information can be input into the wear prediction model to obtain the subsequent wear prediction sequence. When the wear prediction sequence reaches the output standard of the wear prediction model, the wear of the vehicle switch has reached the limit, which will have a certain impact on the failure rate of the vehicle switch. At this time, the vehicle switch should be replaced. When testing the vehicle switch, it can be seen from the characteristics of the key that the elasticity of the vehicle switch will decrease linearly with the increase in the number of uses until it loses its elasticity. After losing elasticity, the rebound speed and rebound depth will not change, so the wear will also remain stable. Therefore, when the wear prediction value in the wear prediction sequence changes slightly or remains unchanged, it reflects that the vehicle switch has lost its elasticity. At this time, the switch wear prediction device will issue a fault warning to the vehicle switch, reminding the target user to replace the vehicle switch in time, thereby reducing the accident rate during vehicle driving.

[0086] In summary, according to the switch wear prediction method, device, electronic device and vehicle provided by the present invention, compared with the prior art, the present invention obtains the target user's pressing information on the vehicle switch at the current stage, the pressing information includes a rebound speed sequence set and a rebound depth sequence set, the rebound speed sequence set includes multiple rebound speed sequences under different pressure information, the rebound depth sequence set includes multiple rebound depth sequences under different pressure information, and the pressure information at least includes pressure duration and pressure size; calculates a first attenuation evaluation value sequence corresponding to the multiple rebound speed sequences, and calculates a second attenuation evaluation value sequence corresponding to the multiple rebound depth sequences; uses the first attenuation evaluation value sequence and the second attenuation evaluation value sequence to calculate the wear evaluation value sequence of the vehicle switch under different pressure information at the current stage; inputs the wear evaluation value sequence into the trained wear prediction model to obtain a wear prediction sequence for the vehicle switch at the next stage. By applying the scheme disclosed in the present invention, the wear prediction model can be used to accurately predict the wear degree of the vehicle switch in the next stage based on the pressing information of the vehicle switch in the current stage. Through this intelligent prediction method, the prediction error of the switch wear degree can be reduced, thereby facilitating accurate estimation of the remaining life of the switch during use, and when the remaining life reaches the set warning value, a fault warning is issued for the vehicle switch, reminding the user to replace the vehicle switch in time, and perform maintenance before the vehicle switch fails, so as to prevent failures during subsequent use and reduce the accident rate during vehicle driving.

[0087] Based on the above Figure 1 and Figure 2 The specific implementation of the method shown in the embodiment provides a switch wear prediction device, such as Figure 3 As shown, the device includes: a first acquisition module 31, a first calculation module 32, a second calculation module 33, and an input module 34;

[0088] The first acquisition module 31 is used to acquire the target user's pressing information on the vehicle switch at the current stage, the pressing information includes a rebound speed sequence set and a rebound depth sequence set, the rebound speed sequence set includes multiple rebound speed sequences under different pressure information, the rebound depth sequence set includes multiple rebound depth sequences under different pressure information, and the pressure information includes at least pressure duration and pressure magnitude;

[0089] A first calculation module 32, used for calculating a first attenuation evaluation value sequence corresponding to a plurality of rebound velocity sequences, and calculating a second attenuation evaluation value sequence corresponding to a plurality of rebound depth sequences;

[0090] The second calculation module 33 is used to calculate the wear evaluation value sequence of the vehicle switch under the action of different pressure information at the current stage by using the first attenuation evaluation value sequence and the second attenuation evaluation value sequence;

[0091] The input module 34 is used to input the wear evaluation value sequence into the trained wear prediction model to obtain the wear prediction sequence of the vehicle switch in the next stage.

[0092] In a specific application scenario, the first calculation module 32 is used to calculate multiple fitting speed line slopes corresponding to multiple rebound speed sequences using the least squares method, and to calculate multiple fitting depth line slopes corresponding to multiple rebound depth sequences using the least squares method; based on the multiple fitting speed line slopes, respectively calculate the rebound speed attenuation evaluation values ​​under different pressure information to obtain a first attenuation evaluation value sequence including multiple rebound speed attenuation evaluation values; based on the multiple fitting depth line slopes, respectively calculate the rebound depth attenuation evaluation values ​​under different pressure information to obtain a second attenuation evaluation value sequence including multiple rebound depth attenuation evaluation values.

[0093] In a specific application scenario, the first calculation module 32 is used to screen the minimum fitting speed line slope and the maximum fitting speed line slope from multiple fitting speed line slopes; for each fitting speed line slope among the multiple fitting speed line slopes, based on the minimum fitting speed line slope and the maximum fitting speed line slope, the calculation process of the rebound speed attenuation evaluation value is repeatedly executed until a first attenuation evaluation value sequence corresponding to multiple rebound speed sequences is obtained; wherein, the calculation process of the rebound speed attenuation evaluation value includes: determining any fitting speed line slope among the multiple fitting speed line slopes as the target fitting speed line slope; calculating a first slope difference between the target fitting speed line slope and the minimum fitting speed line slope, and a second slope difference between the maximum fitting speed line slope and the target fitting speed line slope, and determining the ratio of the first slope difference to the second slope difference as the rebound speed attenuation evaluation value under the action of the pressure information corresponding to the target fitting speed line slope.

[0094] In a specific application scenario, the first calculation module 32 is used to screen the minimum fitting depth line slope and the maximum fitting depth line slope from multiple fitting depth line slopes; for each fitting depth line slope among the multiple fitting depth line slopes, based on the minimum fitting depth line slope and the maximum fitting depth line slope, the calculation process of the rebound depth attenuation evaluation value is repeatedly executed until a second attenuation evaluation value sequence corresponding to multiple rebound depth sequences is obtained; wherein, the calculation process of the rebound depth attenuation evaluation value includes: determining any fitting depth line slope among the multiple fitting depth line slopes as the target fitting depth line slope; calculating the third slope difference between the target fitting depth line slope and the minimum fitting depth line slope, and the fourth slope difference between the maximum fitting depth line slope and the target fitting depth line slope, and determining the ratio of the third slope difference to the fourth slope difference as the rebound depth attenuation evaluation value under the action of the pressure information corresponding to the target fitting depth line slope.

[0095] In a specific application scenario, the second calculation module 33 is used to perform a product operation on the rebound velocity attenuation evaluation value and the rebound depth attenuation evaluation value under different pressure information based on the first attenuation evaluation value sequence and the second attenuation evaluation value sequence to obtain a target attenuation evaluation value sequence under different pressure information; and determine the inverse of the sum of the target attenuation evaluation value sequence and 1 as the wear evaluation value sequence of the vehicle switch under different pressure information.

[0096] In specific application scenarios, such as Figure 4 As shown, the device also includes a training method for the wear prediction model: a second acquisition module 35, a third calculation module 36, and a training module 37;

[0097] The second acquisition module 35 is used to acquire sample pressing information of the target user, the sample pressing information including a first wear evaluation value sequence of the vehicle switch in a first historical stage under different pressure information, and a second wear evaluation value sequence of a second wear evaluation value sequence in a second historical stage, the second historical stage being the next stage of the first historical stage;

[0098] The third calculation module 36 is used to calculate the mass loss influence degree of the first wear degree evaluation value sequence under the action of different pressure information, and group the first wear degree evaluation value sequence based on the mass loss influence degree to obtain multiple clusters; for the same cluster, the sample distance between the first wear degree evaluation value sequences in the cluster is used as the confidence of the corresponding cluster;

[0099] The training module 37 is used to use the first wear evaluation value sequence as the input feature of the wear prediction model, and the second wear evaluation value sequence as the training label of the wear prediction model, and iteratively train the wear prediction model based on the confidence until the loss function value of the wear prediction model is less than a preset threshold, and it is judged that the wear prediction model training is completed.

[0100] In a specific application scenario, the third calculation module 36 can be used to extract the maximum pressure duration, the minimum pressure duration, the maximum pressure magnitude and the minimum pressure magnitude from different pressure information; substitute each pressure information, the maximum pressure duration, the minimum pressure duration, the maximum pressure magnitude and the minimum pressure magnitude into the quality loss influence degree calculation formula to obtain the quality loss influence degree of the first wear degree evaluation value sequence under the action of different pressure information;

[0101] Among them, the calculation formula for the degree of quality loss includes:

[0102]

[0103] In the formula, Q1 represents the degree of quality loss, F i Indicates the magnitude of each pressure in different pressure information, FMin Indicates the minimum pressure, F Max Indicates the maximum pressure, M i Indicates the current pressure time, M Min Indicates the minimum pressure duration, M Max Indicates the duration of maximum pressure.

[0104] It should be noted that for other corresponding descriptions of the functional units involved in the switch wear prediction device provided in this embodiment, reference can be made to Figure 1 and Figure 2 The corresponding description in will not be repeated here.

[0105] Based on the above Figure 1 and Figure 2 The method shown in the embodiment also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned Figure 1 and Figure 2 The method shown.

[0106] Based on this understanding, the technical solution of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of various implementation scenarios of the present disclosure.

[0107] Based on the above Figure 1 and Figure 2 The method shown, and Figure 3 and Figure 4 In order to achieve the above-mentioned purpose, the embodiment of the present disclosure also provides an electronic device that can be configured on the vehicle (such as an electric vehicle) side, and the device includes a storage medium and a processor; the storage medium is used to store a computer program; the processor is used to execute the computer program to achieve the above-mentioned Figure 1 and Figure 2 The method shown.

[0108] Optionally, the above-mentioned physical device may also include a user interface, a network interface, a camera, a radio frequency (RF) circuit, a sensor, an audio circuit, a WI-FI module, etc. The user interface may include a display, an input unit such as a keyboard, etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (such as a WI-FI interface), etc.

[0109] Those skilled in the art will appreciate that the above-mentioned physical device structure provided in this embodiment does not constitute a limitation on the physical device, and may include more or fewer components, or a combination of certain components, or different arrangements of components.

[0110] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the above-mentioned physical device, and supports the operation of the information processing program and other software and / or programs. The network communication module is used to realize the communication between the components inside the storage medium, and the communication with other hardware and software in the information processing physical device.

[0111] Based on the above electronic device, the embodiment of the present disclosure further provides a vehicle, which may specifically include: the above electronic device. The vehicle may specifically be an electric car, etc.

[0112] Through the description of the above implementation methods, the technical personnel in this field can clearly understand that the present disclosure can be implemented by means of software plus the necessary general hardware platform, or by hardware. Compared with the prior art, the technical solution in the present disclosure obtains the target user's pressing information on the vehicle switch at the current stage, the pressing information includes a rebound speed sequence set and a rebound depth sequence set, the rebound speed sequence set includes multiple rebound speed sequences under different pressure information, the rebound depth sequence set includes multiple rebound depth sequences under different pressure information, and the pressure information at least includes pressure duration and pressure size; calculates the first attenuation evaluation value sequence corresponding to the multiple rebound speed sequences, and calculates the second attenuation evaluation value sequence corresponding to the multiple rebound depth sequences; uses the first attenuation evaluation value sequence and the second attenuation evaluation value sequence to calculate the wear evaluation value sequence of the vehicle switch under different pressure information at the current stage; inputs the wear evaluation value sequence into the trained wear prediction model to obtain the wear prediction sequence of the vehicle switch at the next stage. By applying the scheme disclosed in the present invention, the wear prediction model can be used to accurately predict the wear degree of the vehicle switch in the next stage based on the pressing information of the vehicle switch in the current stage. Through this intelligent prediction method, the prediction error of the switch wear degree can be reduced, thereby facilitating accurate estimation of the remaining life of the switch during use, and when the remaining life reaches the set warning value, a fault warning is issued for the vehicle switch, reminding the user to replace the vehicle switch in time, and perform maintenance before the vehicle switch fails, so as to prevent failures during subsequent use and reduce the accident rate during vehicle driving.

[0113] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprising a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0114] The above are only specific embodiments of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to these embodiments herein, but will conform to the widest scope consistent with the principles and novel features applied herein.

Claims

1. A switch wear prediction method, characterized in that: The method comprises: Acquire the target user's pressing information on the vehicle switch at the current stage, wherein the pressing information includes a rebound speed sequence set and a rebound depth sequence set, wherein the rebound speed sequence set includes multiple rebound speed sequences under different pressure information, and the rebound depth sequence set includes multiple rebound depth sequences under different pressure information, and the pressure information includes at least pressure duration and pressure magnitude; Calculating a first attenuation evaluation value sequence corresponding to the plurality of rebound speed sequences, and calculating a second attenuation evaluation value sequence corresponding to the plurality of rebound depth sequences; Calculate the wear evaluation value sequence of the vehicle switch under different pressure information at the current stage by using the first attenuation evaluation value sequence and the second attenuation evaluation value sequence; The wear evaluation value sequence is input into the trained wear prediction model to obtain the wear prediction sequence of the vehicle switch in the next stage.

2. The method according to claim 1, characterized in that The calculating of the first attenuation evaluation value sequences corresponding to the plurality of rebound speed sequences, and the calculating of the second attenuation evaluation value sequences corresponding to the plurality of rebound depth sequences, include: Calculating a plurality of fitted velocity straight line slopes corresponding to the plurality of rebound velocity sequences by using a least square method, and calculating a plurality of fitted depth straight line slopes corresponding to the plurality of rebound depth sequences by using the least square method; Based on the multiple fitting speed straight line slopes, respectively calculate the rebound speed attenuation evaluation values ​​under the action of different pressure information to obtain a first attenuation evaluation value sequence including multiple rebound speed attenuation evaluation values; The rebound depth attenuation evaluation values ​​under the action of different pressure information are calculated based on the slopes of the multiple fitting depth lines, so as to obtain a second attenuation evaluation value sequence including multiple rebound depth attenuation evaluation values.

3. The method according to claim 2, characterized in that The rebound velocity attenuation evaluation values ​​under different pressure information are calculated based on the multiple fitting velocity straight line slopes to obtain a first attenuation evaluation value sequence including multiple rebound velocity attenuation evaluation values, including: Selecting a minimum fitting speed straight line slope and a maximum fitting speed straight line slope from the plurality of fitting speed straight line slopes; For each of the multiple fitting speed line slopes, the calculation process of the rebound speed attenuation evaluation value is repeatedly performed based on the minimum fitting speed line slope and the maximum fitting speed line slope, until a first attenuation evaluation value sequence corresponding to the multiple rebound speed sequences is obtained; The calculation process of the rebound velocity attenuation evaluation value includes: Determine any one of the plurality of fitted speed straight line slopes as a target fitted speed straight line slope; A first slope difference between the target fitting speed line slope and the minimum fitting speed line slope, and a second slope difference between the maximum fitting speed line slope and the target fitting speed line slope are calculated, and a ratio of the first slope difference to the second slope difference is determined as a rebound speed attenuation evaluation value under the pressure information corresponding to the target fitting speed line slope.

4. The method according to claim 2, characterized in that: The rebound depth attenuation evaluation values ​​under different pressure information are calculated based on the slopes of the multiple fitting depth lines to obtain a second attenuation evaluation value sequence including multiple rebound depth attenuation evaluation values, including: Screening a minimum fitting depth straight line slope and a maximum fitting depth straight line slope from the plurality of fitting depth straight line slopes; For each of the multiple fitting depth straight line slopes, the calculation process of the rebound depth attenuation evaluation value is repeatedly performed based on the minimum fitting depth straight line slope and the maximum fitting depth straight line slope, until a second attenuation evaluation value sequence corresponding to the multiple rebound depth sequences is obtained; The calculation process of the rebound depth attenuation evaluation value includes: Determining any one of the plurality of fitting depth straight line slopes as a target fitting depth straight line slope; Calculate the third slope difference between the target fitting depth straight line slope and the minimum fitting depth straight line slope, and the fourth slope difference between the maximum fitting depth straight line slope and the target fitting depth straight line slope, and determine the ratio of the third slope difference to the fourth slope difference as the rebound depth attenuation evaluation value under the pressure information corresponding to the target fitting depth straight line slope.

5. The method according to claim 1, characterized in that The step of calculating the wear evaluation value sequence of the vehicle switch under different pressure information at the current stage by using the first attenuation evaluation value sequence and the second attenuation evaluation value sequence includes: Based on the first attenuation evaluation value sequence and the second attenuation evaluation value sequence, a product operation is performed on the rebound speed attenuation evaluation value and the rebound depth attenuation evaluation value under different pressure information to obtain a target attenuation evaluation value sequence under different pressure information; The reciprocal of the sum of the target attenuation evaluation value sequence and 1 is determined as the wear evaluation value sequence of the vehicle switch under the action of different pressure information.

6. The method according to any one of claims 1 to 5, characterized in that: The method also includes a training method for the wear prediction model: Acquire sample pressing information of the target user, the sample pressing information including a first wear evaluation value sequence of the vehicle switch in a first historical stage and a second wear evaluation value sequence of a second historical stage under different pressure information, wherein the second historical stage is a stage next to the first historical stage; calculating the mass loss influence degree of the first wear evaluation value sequence under different pressure information, and grouping the first wear evaluation value sequence based on the mass loss influence degree to obtain a plurality of clusters; for the same cluster, taking the sample distance between the first wear evaluation value sequences in the cluster as the confidence of the corresponding cluster; The first wear evaluation value sequence is used as the input feature of the wear prediction model, and the second wear evaluation value sequence is used as the training label of the wear prediction model. The wear prediction model is iteratively trained based on the confidence level until the loss function value of the wear prediction model is less than a preset threshold, and it is determined that the training of the wear prediction model is completed.

7. The method according to claim 6, characterized in that The calculating the mass loss influence degree of the first wear evaluation value sequence under different pressure information includes: Extract the maximum pressure duration, minimum pressure duration, maximum pressure magnitude and minimum pressure magnitude from different pressure information; Substituting each pressure information, the maximum pressure duration, the minimum pressure duration, the maximum pressure magnitude and the minimum pressure magnitude into a quality loss influence degree calculation formula to obtain the quality loss influence degree of the first wear degree evaluation value sequence under different pressure information; The calculation formula for the degree of influence of mass loss includes: Where Q1 represents the degree of influence of the quality loss, F i Indicates the magnitude of each pressure in the different pressure information, F Min Indicates the minimum pressure, F Max Indicates the maximum pressure, M i Indicates the current pressure time, M Min Indicates the minimum pressure duration, M Max Indicates the duration of the maximum pressure.

8. A switch wear prediction device, characterized in that: include: A first acquisition module is used to acquire the target user's pressing information on the vehicle switch at the current stage, wherein the pressing information includes a rebound speed sequence set and a rebound depth sequence set, wherein the rebound speed sequence set includes a plurality of rebound speed sequences under different pressure information, and the rebound depth sequence set includes a plurality of rebound depth sequences under different pressure information, and the pressure information includes at least pressure duration and pressure magnitude; A first calculation module, used for calculating a first attenuation evaluation value sequence corresponding to the plurality of rebound speed sequences, and calculating a second attenuation evaluation value sequence corresponding to the plurality of rebound depth sequences; A second calculation module, configured to calculate a wear evaluation value sequence of the vehicle switch under different pressure information at a current stage by using the first attenuation evaluation value sequence and the second attenuation evaluation value sequence; The input module is used to input the wear evaluation value sequence into the trained wear prediction model to obtain the wear prediction sequence of the vehicle switch in the next stage.

9. An electronic device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-7.

11. A vehicle, characterized in that: include: The electronic device as claimed in claim 9.

Images